fix(openrouter): strip openrouter/ prefix from model ID in normalizeResolvedModel hook (fixes #92611) by liuhao1024 · Pull Request #92627 · openclaw/openclaw

liuhao1024 · 2026-06-13T07:42:58Z

Summary

Normalize provider-qualified OpenRouter model IDs before transport, so openrouter/anthropic/claude-sonnet-4.6 reaches the API as anthropic/claude-sonnet-4.6.
Preserve native OpenRouter namespace IDs such as openrouter/auto; stripping every openrouter/ prefix would break valid upstream IDs.
Use the normalized API ID for capability cache loading and lookup, avoiding fallback text-only/reasoning/token metadata on the repaired path.
Add core, plugin, and live regressions for both nested provider-qualified IDs and native OpenRouter IDs.

Verification

node scripts/run-vitest.mjs extensions/openrouter/index.test.ts src/agents/embedded-agent-runner/model.test.ts src/llm/providers/openai-completions.test.ts (178 tests)
pnpm tsgo:extensions:test
pnpm build
Fresh autoreview: clean, no accepted/actionable findings
AWS Crabbox check:changed: cbx_8774c1f7dea1, run run_b542d858e7f9
Live OpenRouter forced tool calls:
- openrouter/anthropic/claude-sonnet-4.6
- openrouter/auto
Direct provider regression guards:
- OpenAI Responses gpt-5.4-mini forced get_weather
- Anthropic Messages claude-sonnet-4-6 forced get_weather

Real behavior proof

Behavior addressed: OpenRouter provider-qualified model IDs no longer produce invalid API model IDs or fallback capability metadata.

Real environment tested: Live OpenRouter, OpenAI, and Anthropic APIs from the maintainer checkout; Linux CI-parity checks on AWS Crabbox.

Exact steps or command run after this patch: Ran the focused Vitest command above, live OpenRouter plugin test for both model refs, direct forced-tool API probes, extension typecheck, full build, and remote check:changed.

Evidence after fix: Copied live console output:

OpenRouter openrouter/anthropic/claude-sonnet-4.6:
Test Files  1 passed (1)
Tests       1 passed | 2 skipped (3)

OpenRouter openrouter/auto:
Test Files  1 passed (1)
Tests       1 passed | 2 skipped (3)

__OPENROUTER_LIVE_FINAL__:0
OpenAI Responses forced tool call: PASS
Anthropic Messages forced tool call: PASS

Observed result after fix: The nested OpenRouter qualifier is removed only where required, native openrouter/* API IDs remain intact, and both forms complete real forced tool calls with canonical capability metadata.

What was not tested: No known gaps.

Release-note context

Release-note context: fixes OpenRouter HTTP 400 failures for provider-qualified model IDs while retaining native OpenRouter routes.

clawsweeper · 2026-06-13T07:44:39Z

Codex review: needs maintainer review before merge. Reviewed June 13, 2026, 7:02 AM ET / 11:02 UTC.

Summary
The branch adds OpenRouter API-model-id normalization in the provider resolved-model and capability lookup paths, preserves native OpenRouter IDs, and expands plugin/core/live tests.

PR surface: Source +23, Tests +229. Total +252 across 5 files.

Reproducibility: yes. at source level. Current main sends the resolved OpenRouter model.id through the request payload unchanged, and the live OpenRouter catalog shows anthropic/claude-sonnet-4.6 plus openrouter/auto, not openrouter/anthropic/claude-sonnet-4.6 or auto.

Review metrics: 1 noteworthy metric.

API-facing model-id normalization: 1 provider hook plus dynamic capability lookup path changed. The change affects the model id sent to OpenRouter and the metadata key used before transport, which is the compatibility-sensitive part of the PR.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

[P2] Refresh or override the repository proof label/check before merge if it still reports mock-only proof despite the supplied live evidence.

Risk before merge

[P1] The PR changes API-facing OpenRouter model ids for slash-bearing refs, so maintainers should treat it as compatibility-sensitive provider routing even though the targeted live proof supports the rule.

Maintainer options:

Land with explicit provider-routing acceptance (recommended)
Because the branch preserves openrouter/auto and has live OpenRouter proof, maintainers can accept the remaining compatibility risk once required checks are green.
Ask for a broader OpenRouter live matrix
If maintainers want more upgrade confidence, require one additional live nested non-Anthropic OpenRouter model before merge.
Pause if proof gates stay stale
If repository proof automation still rejects the supplied live proof, pause for a maintainer override or proof-format refresh rather than changing the code again.

Next step before merge

[P2] No automated code repair is indicated; the remaining action is maintainer review of the compatibility-sensitive provider-routing change and proof gate state.

Security
Cleared: The diff changes provider runtime normalization and tests only; it does not modify dependencies, workflows, secrets, permissions, package metadata, or downloaded-code execution paths.

Review details

Best possible solution:

Land the narrowed OpenRouter-owned normalization as the canonical fix after maintainer review, keep openrouter/auto preserved, and let the linked bug close only after this PR merges.

Do we have a high-confidence way to reproduce the issue?

Yes, at source level. Current main sends the resolved OpenRouter model.id through the request payload unchanged, and the live OpenRouter catalog shows anthropic/claude-sonnet-4.6 plus openrouter/auto, not openrouter/anthropic/claude-sonnet-4.6 or auto.

Is this the best way to solve the issue?

Yes. The provider-owned normalizeResolvedModel hook is the right layer; changing generic OpenAI-compatible transport would mix OpenRouter-specific ID policy into shared runtime code.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against d3e7e0366907.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body and maintainer comment provide live OpenRouter forced-tool proof for both the nested Anthropic route and openrouter/auto, plus direct provider guards and Crabbox changed-gate evidence.
add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body and maintainer comment provide live OpenRouter forced-tool proof for both the nested Anthropic route and openrouter/auto, plus direct provider guards and Crabbox changed-gate evidence.
remove rating: 🧂 unranked krab: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.
remove status: 📣 needs proof: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

P2: This is a bounded OpenRouter provider-routing bugfix with limited blast radius to OpenRouter users.
merge-risk: 🚨 compatibility: The PR changes how existing slash-bearing OpenRouter model refs are normalized during runtime upgrades.
merge-risk: 🚨 auth-provider: The changed path controls OpenRouter provider/model routing and can determine whether the upstream API accepts the request.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body and maintainer comment provide live OpenRouter forced-tool proof for both the nested Anthropic route and openrouter/auto, plus direct provider guards and Crabbox changed-gate evidence.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body and maintainer comment provide live OpenRouter forced-tool proof for both the nested Anthropic route and openrouter/auto, plus direct provider guards and Crabbox changed-gate evidence.

Evidence reviewed

PR surface:

Source +23, Tests +229. Total +252 across 5 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	2	27	4	+23
Tests	3	239	10	+229
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	5	266	14	+252

What I checked:

Current transport uses resolved model id: Current main sends model.id as the OpenAI-compatible request model field, so provider resolved-model normalization controls the API-facing OpenRouter slug. (src/agents/openai-transport-stream.ts:4097, d3e7e0366907)
Provider hook is the intended seam: The plugin SDK documents normalizeResolvedModel as provider-owned transport normalization for API ids, base URLs, and compat quirks, which fits this OpenRouter-only fix better than changing the generic OpenAI transport. (src/plugins/types.ts:1336, d3e7e0366907)
PR preserves native OpenRouter namespace ids: PR head adds normalizeOpenRouterApiModelId, stripping openrouter/ only when the remainder is still namespaced, so openrouter/auto is preserved while openrouter/anthropic/... becomes anthropic/.... (extensions/openrouter/models.ts:27, 0e4be842fa1e)
PR normalizes runtime and metadata lookup paths: PR head applies the API-id normalizer in the resolved-model hook and uses the same normalized key for OpenRouter capability loading/lookup. (extensions/openrouter/index.ts:54, 0e4be842fa1e)
Regression coverage covers both sides: PR head tests capability lookup for openrouter/anthropic/claude-sonnet-4.6, preserves openrouter/auto, and normalizes duplicated openrouter/openrouter/auto to the native upstream id. (extensions/openrouter/index.test.ts:225, 0e4be842fa1e)
OpenRouter catalog contract checked: The live OpenRouter models endpoint contains openrouter/auto and anthropic/claude-sonnet-4.6, and does not contain auto or openrouter/anthropic/claude-sonnet-4.6.

Likely related people:

steipete: Current-line blame for the OpenRouter hook points to a recent OpenRouter change, and this account merged or authored adjacent provider-prefix fixes including fix(agents): normalize prefixed Anthropic fallback model ids (#88560) #88587 and fix(models): strip remaining provider self prefixes #88781. (role: recent area contributor and merger; confidence: high; commits: 8c7e5c691891, 7dd7cdcbe6d6, 826b378452e4; files: extensions/openrouter/index.ts, extensions/openrouter/models.ts, packages/model-catalog-core/src/provider-model-id-normalization.ts)
TurboTheTurtle: Authored the merged Anthropic prefixed-model normalization fix in fix(agents): normalize prefixed Anthropic fallback model ids (#88560) #88587, which is adjacent to this provider-prefix routing issue. (role: recent related fix author; confidence: medium; commits: 4ee13a12c08d, 826b378452e4; files: packages/model-catalog-core/src/provider-model-id-normalization.ts, src/agents/embedded-agent-runner/model.test.ts, src/agents/model-fallback.test.ts)
charles-openclaw: Authored the merged provider self-prefix stripping PR that shaped the nearby catalog-vs-runtime normalization boundary. (role: recent related fix author; confidence: medium; commits: 36f07b37d83b, 84266cd30e91; files: packages/model-catalog-core/src/provider-model-id-normalization.ts, src/agents/model-selection-normalize.ts)
Vincent Koc: Git history shows adjacent work on OpenRouter base-url healing and the LLM transport adapter seam that this provider hook relies on. (role: adjacent provider/runtime seam contributor; confidence: low; commits: 791dbf4f9dde, 4798e125f40c; files: extensions/openrouter/index.ts, src/llm/providers/openai-completions.ts, src/agents/openai-transport-stream.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

…esolvedModel hook The normalizeOpenRouterResolvedModel hook normalizes baseUrl and reasoning but did not normalize model.id. When OpenClaw registers an OpenRouter model with ID 'openrouter/anthropic/claude-sonnet-4.6', that full string was sent to the OpenRouter API, which expects 'anthropic/claude-sonnet-4.6'. Uses the existing normalizeOpenRouterModelId() from ./models.js which already strips the 'openrouter/' prefix. Adds model ID to the early-return check so models without the prefix pass through unchanged. Fixes openclaw#92611

steipete · 2026-06-13T10:55:58Z

Land-ready verification for 0e4be842fa1e58b7ee8c087953d764beaa23f6c2.

Focused regression suite: node scripts/run-vitest.mjs extensions/openrouter/index.test.ts src/agents/embedded-agent-runner/model.test.ts src/llm/providers/openai-completions.test.ts (178 passed)
Extension test types: pnpm tsgo:extensions:test
Build: pnpm build
Fresh autoreview: clean; no accepted/actionable findings
Live OpenRouter:
- OPENCLAW_LIVE_TEST=1 OPENCLAW_LIVE_OPENROUTER_PLUGIN_MODEL=openrouter/anthropic/claude-sonnet-4.6 node scripts/test-live.mjs -- extensions/openrouter/openrouter.live.test.ts -t "normalizes a prefixed OpenRouter model and completes a live tool call"
- OPENCLAW_LIVE_TEST=1 OPENCLAW_LIVE_OPENROUTER_PLUGIN_MODEL=openrouter/auto node scripts/test-live.mjs -- extensions/openrouter/openrouter.live.test.ts -t "normalizes a prefixed OpenRouter model and completes a live tool call"
- Both completed forced get_weather calls.
Direct official-provider guards:
- OpenAI Responses gpt-5.4-mini: forced get_weather passed.
- Anthropic Messages claude-sonnet-4-6: forced get_weather passed.
Remote changed gate: env OPENCLAW_CHECK_CHANGED_REMOTE_CHILD=1 OPENCLAW_CHANGED_LANES_RAW_SYNC=1 corepack pnpm check:changed
- AWS Crabbox cbx_8774c1f7dea1
- Run run_b542d858e7f9
- Core/extension typechecks, lint, boundary guards, and import-cycle checks passed.

Known proof gaps: none for the reported OpenRouter behavior.

Normalize provider-qualified OpenRouter model IDs before capability lookup and transport while preserving native OpenRouter namespace IDs. Fixes openclaw#92611. Co-authored-by: liuhao1024 <[email protected]>

…26.6.8) (#1144) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.6` → `2026.6.8` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.8`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202668) [Compare Source](openclaw/openclaw@v2026.6.6...v2026.6.8) ##### Highlights - Telegram and WhatsApp channel delivery are richer and less brittle: Telegram can send structured rich text with tables, lists, expandable blockquotes, prompt-preserving CLI backend delivery, retired native draft migration, and safer rich-media boundaries, while WhatsApp now honors configured ACP bindings. ([#92679](openclaw/openclaw#92679), [#84082](openclaw/openclaw#84082), [#89421](openclaw/openclaw#89421), [#92513](openclaw/openclaw#92513)) Thanks [@obviyus](https://github.com/obviyus), [@jzakirov](https://github.com/jzakirov), [@spacegeologist](https://github.com/spacegeologist), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agent and Gateway recovery is sharper across account-scoped DM sends, generated media completions, restart shutdown aborts, yielded subagent pauses, yielded cron media, heartbeat dedupe, session identity prompts, and unknown OpenAI agent selector rejection. ([#92788](openclaw/openclaw#92788), [#91246](openclaw/openclaw#91246), [#91357](openclaw/openclaw#91357), [#92631](openclaw/openclaw#92631), [#92146](openclaw/openclaw#92146), [#91287](openclaw/openclaw#91287), [#92468](openclaw/openclaw#92468), [#92510](openclaw/openclaw#92510)) Thanks [@yetval](https://github.com/yetval), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@ooiuuii](https://github.com/ooiuuii), [@openperf](https://github.com/openperf), [@IWhatsskill](https://github.com/IWhatsskill), [@ZengWen-DT](https://github.com/ZengWen-DT), and [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Provider/model handling expands and tightens with GLM-5.2, Claude Haiku 4.5 catalog rows, OpenRouter and Google Vertex provider-prefix normalization, managed SecretRef auth, bounded model browse discovery, storeless OpenAI Responses replay gating, and Claude 4.5 Copilot tool-streaming safety. ([#92796](openclaw/openclaw#92796), [#90116](openclaw/openclaw#90116), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218), [#90686](openclaw/openclaw#90686), [#92247](openclaw/openclaw#92247), [#90706](openclaw/openclaw#90706), [#75393](openclaw/openclaw#75393)) Thanks [@arkyu2077](https://github.com/arkyu2077), [@liuhao1024](https://github.com/liuhao1024), [@bymle](https://github.com/bymle), [@rohitjavvadi](https://github.com/rohitjavvadi), [@samson910022](https://github.com/samson910022), [@snowzlm](https://github.com/snowzlm), and [@Kailigithub](https://github.com/Kailigithub). - `/usage` and reply payload hooks now have a native full footer renderer, default template, fixed-decimal formatting, credential-aware limits, better partial-count handling, and warnings for broken templates instead of silent bad output. ([#92657](openclaw/openclaw#92657), [#89835](openclaw/openclaw#89835), [#89629](openclaw/openclaw#89629)) Thanks [@Marvinthebored](https://github.com/Marvinthebored). - UI and mobile flows are steadier: workspace files can collapse and start collapsed, WebChat backscroll survives streaming, the sidebar session picker remains interactive above the desktop workbench, reset soft args survive UI dispatch, stale dashboard session parent lineage is preserved, and iOS reconnects stale foreground gateways. ([#92779](openclaw/openclaw#92779), [#92622](openclaw/openclaw#92622), [#92705](openclaw/openclaw#92705), [#91353](openclaw/openclaw#91353), [#90658](openclaw/openclaw#90658), [#92552](openclaw/openclaw#92552)) Thanks [@shakkernerd](https://github.com/shakkernerd), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@NianJiuZst](https://github.com/NianJiuZst), [@zhouhe-xydt](https://github.com/zhouhe-xydt), [@luoyanglang](https://github.com/luoyanglang), and [@Solvely-Colin](https://github.com/Solvely-Colin). - Memory, state, and diagnostics recover cleaner: oversized OpenAI embedding batches split before 431s, QMD memory search stays available in transient mode, SQLite avoids WAL on NFS state volumes, stuck-session recovery scheduling no longer resets warning backoff, and Infinity chunk limits stay genuinely unbounded. ([#92650](openclaw/openclaw#92650), [#92618](openclaw/openclaw#92618), [#92639](openclaw/openclaw#92639), [#91247](openclaw/openclaw#91247), [#92752](openclaw/openclaw#92752), [#92735](openclaw/openclaw#92735)) Thanks [@mushuiyu886](https://github.com/mushuiyu886), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@849261680](https://github.com/849261680), [@gnanam1990](https://github.com/gnanam1990), and [@yhterrance](https://github.com/yhterrance). ##### Changes - Providers/models: add GLM-5.2 support and Claude Haiku 4.5 catalog entries while keeping provider-qualified model IDs normalized across OpenRouter and Google Vertex paths. ([#92796](openclaw/openclaw#92796), [#90116](openclaw/openclaw#90116), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218)) Thanks [@arkyu2077](https://github.com/arkyu2077), [@liuhao1024](https://github.com/liuhao1024), and [@bymle](https://github.com/bymle). - Channel plugins: ship Telegram rich-message delivery and WhatsApp ACP binding support, including rich prompt handoff to CLI backends and transport fixtures for richer drafts. ([#92679](openclaw/openclaw#92679), [#92513](openclaw/openclaw#92513)) Thanks [@obviyus](https://github.com/obviyus) and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agent commands: support `/btw` in CLI-backed sessions and keep CLI usage-error exits classified as usage failures instead of successful runs. ([#92669](openclaw/openclaw#92669), [#92162](openclaw/openclaw#92162)) Thanks [@joshavant](https://github.com/joshavant) and [@Pandah97](https://github.com/Pandah97). - Usage hooks: add built-in full footer rendering, default footer templates, per-turn usage state, credential-aware limits, and fixed-decimal formatting for usage-bar templates. ([#92657](openclaw/openclaw#92657), [#89835](openclaw/openclaw#89835), [#89629](openclaw/openclaw#89629)) Thanks [@Marvinthebored](https://github.com/Marvinthebored). - Docs and operator guidance: document node config examples, clarify before-install hook scope, correct agent default concurrency comments, refresh ZAI provider docs, and update channel/group docs for current Telegram and WhatsApp behavior. ([#92677](openclaw/openclaw#92677), [#92766](openclaw/openclaw#92766), [#92695](openclaw/openclaw#92695)) Thanks [@liuhao1024](https://github.com/liuhao1024), [@sallyom](https://github.com/sallyom), and [@ArielSmoliar](https://github.com/ArielSmoliar). ##### Fixes - Onboarding/skills: show the Homebrew install recommendation only on macOS and Linux, so FreeBSD and other unsupported platforms no longer get a misleading brew prompt. Fixes [#68893](openclaw/openclaw#68893); carries forward [#68894](openclaw/openclaw#68894), [#68910](openclaw/openclaw#68910), [#68941](openclaw/openclaw#68941), [#68943](openclaw/openclaw#68943), [#69002](openclaw/openclaw#69002), and [#69545](openclaw/openclaw#69545). Thanks [@yurivict](https://github.com/yurivict), [@Sanjays2402](https://github.com/Sanjays2402), [@Eruditi](https://github.com/Eruditi), [@JustInCache](https://github.com/JustInCache), [@nnish16](https://github.com/nnish16), and [@Mlightsnow](https://github.com/Mlightsnow). - Channels and delivery: preserve account-scoped DM channel send policy, rich Telegram final replies, rich Telegram tables and lists, Telegram thread-create CLI remapping, Slack outbound `message_sent` hooks, contributed message-tool schema optionality, same-channel generated media completions, and channel chunking around surrogate pairs and Infinity limits. ([#92788](openclaw/openclaw#92788), [#92679](openclaw/openclaw#92679), [#89421](openclaw/openclaw#89421), [#89943](openclaw/openclaw#89943), [#91137](openclaw/openclaw#91137), [#91246](openclaw/openclaw#91246), [#92735](openclaw/openclaw#92735)) Thanks [@yetval](https://github.com/yetval), [@obviyus](https://github.com/obviyus), [@spacegeologist](https://github.com/spacegeologist), [@rishitamrakar](https://github.com/rishitamrakar), [@lundog](https://github.com/lundog), [@TurboTheTurtle](https://github.com/TurboTheTurtle), and [@yhterrance](https://github.com/yhterrance). - Auto-reply/groups: keep ordinary group text replies on automatic final-reply delivery while allowing `message(action=send)` for files, images, and other attachments to the same group or topic. Carries forward [#43276](openclaw/openclaw#43276); refs [#48004](openclaw/openclaw#48004). Thanks [@NayukiChiba](https://github.com/NayukiChiba) and [@ShakaRover](https://github.com/ShakaRover). - Auto-reply/skills: preserve multiline payloads for `/skill` and direct skill slash commands while keeping command-head normalization for aliases, colon syntax, and bot mentions. Fixes [#79155](openclaw/openclaw#79155); carries forward [#81305](openclaw/openclaw#81305). Thanks [@web3blind](https://github.com/web3blind). - iMessage: normalize leading NUL sent-message echo prefixes while preserving interior NUL bytes and the leading attributedBody marker handling from [#73942](openclaw/openclaw#73942). Carries forward [#63581](openclaw/openclaw#63581). Thanks [@drvoss](https://github.com/drvoss). - Discord: give generated auto-thread titles a 60-second timeout and 4,096-token reasoning-model output budget, clamped to the selected model output cap. ([#64734](openclaw/openclaw#64734)) Thanks [@hanamizuki](https://github.com/hanamizuki). - Agent, cron, and Gateway runtime: mark active main sessions before restart shutdown aborts, pause yielded subagent runs whose terminal also signals abort, preserve yielded media completions, de-duplicate main-session heartbeat events, expose session identity in runtime prompts, reject unknown OpenAI agent selectors, keep generated media completions and slash-command block replies in WebChat, preserve fresh post-compaction usage while clearing stale usage snapshots, and require admin privileges for HTTP session/model override surfaces. ([#91357](openclaw/openclaw#91357), [#92631](openclaw/openclaw#92631), [#92146](openclaw/openclaw#92146), [#91287](openclaw/openclaw#91287), [#92468](openclaw/openclaw#92468), [#92510](openclaw/openclaw#92510), [#91246](openclaw/openclaw#91246), [#50795](openclaw/openclaw#50795), [#50845](openclaw/openclaw#50845), [#82874](openclaw/openclaw#82874), [#92651](openclaw/openclaw#92651), [#92646](openclaw/openclaw#92646)) Thanks [@ooiuuii](https://github.com/ooiuuii), [@openperf](https://github.com/openperf), [@IWhatsskill](https://github.com/IWhatsskill), [@ZengWen-DT](https://github.com/ZengWen-DT), [@zhangguiping-xydt](https://github.com/zhangguiping-xydt), [@Hollychou924](https://github.com/Hollychou924), [@leno23](https://github.com/leno23), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agents/exec: default empty-success background completion notices on only for real chat channels, preserving explicit opt-outs and keeping generic providers silent while carrying forward the narrow UX intent from [#39726](openclaw/openclaw#39726) and [#46926](openclaw/openclaw#46926). Thanks [@Sapientropic](https://github.com/Sapientropic) and [@wenkang-xie](https://github.com/wenkang-xie). - Providers and model replay: preserve storeless OpenAI Responses replay compatibility, avoid eager tool streaming for Claude 4.5 in Copilot, honor profile auth for SecretRef model entries, bound model browsing, strip provider prefixes where runtimes need bare IDs, and surface nested embedding fetch failures. ([#90706](openclaw/openclaw#90706), [#75393](openclaw/openclaw#75393), [#90686](openclaw/openclaw#90686), [#92247](openclaw/openclaw#92247), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218), [#92628](openclaw/openclaw#92628)) Thanks [@snowzlm](https://github.com/snowzlm), [@Kailigithub](https://github.com/Kailigithub), [@rohitjavvadi](https://github.com/rohitjavvadi), [@samson910022](https://github.com/samson910022), [@liuhao1024](https://github.com/liuhao1024), [@bymle](https://github.com/bymle), and [@mushuiyu886](https://github.com/mushuiyu886). - Memory, state, diagnostics, and config: split header-too-large embedding batches, keep QMD memory search enabled in transient mode, avoid SQLite WAL on NFS volumes, preserve recovery scheduling outside stuck-session warning backoff, and keep shell environment fallbacks contained in config write tests. ([#92650](openclaw/openclaw#92650), [#92618](openclaw/openclaw#92618), [#92639](openclaw/openclaw#92639), [#91247](openclaw/openclaw#91247), [#92752](openclaw/openclaw#92752)) Thanks [@mushuiyu886](https://github.com/mushuiyu886), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@849261680](https://github.com/849261680), and [@gnanam1990](https://github.com/gnanam1990). - Workspace setup state: store setup completion outside the workspace dot directory using an OpenClaw-named root file, migrate valid legacy state forward, and avoid clobbering generic root `workspace-state.json` files for TigerFS-style dot-path compatibility. This Clownfish replacement carries forward the focused [#53326](openclaw/openclaw#53326) fix idea because the original branch was closed and uneditable. ([#53326](openclaw/openclaw#53326), [#44783](openclaw/openclaw#44783), [#39446](openclaw/openclaw#39446)) Thanks [@1qh](https://github.com/1qh). - UI/mobile/TUI: preserve dashboard session parent lineage, WebChat backscroll, reset soft command args, sidebar session picker interactivity, collapsed workspace files, resolved `/model` confirmation refs, and stale foreground iOS Gateway reconnects. ([#90658](openclaw/openclaw#90658), [#92622](openclaw/openclaw#92622), [#91353](openclaw/openclaw#91353), [#92705](openclaw/openclaw#92705), [#92779](openclaw/openclaw#92779), [#92773](openclaw/openclaw#92773), [#92552](openclaw/openclaw#92552)) Thanks [@luoyanglang](https://github.com/luoyanglang), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@zhouhe-xydt](https://github.com/zhouhe-xydt), [@NianJiuZst](https://github.com/NianJiuZst), [@shakkernerd](https://github.com/shakkernerd), [@NarahariRaghava](https://github.com/NarahariRaghava), and [@Solvely-Colin](https://github.com/Solvely-Colin). - TUI: reload the active session after external `/new` or `/reset` session-change events so stale transcript and stream state clear promptly. Fixes [#38966](openclaw/openclaw#38966); carries forward [#40472](openclaw/openclaw#40472). Thanks [@yizhanzjz](https://github.com/yizhanzjz) and [@wsyjh8](https://github.com/wsyjh8). - Control UI: preserve Gateway Access tokens during same-normalized WebSocket URL edits and reload gateway-scoped tokens when switching endpoints. Fixes [#41545](openclaw/openclaw#41545); repairs [#42001](openclaw/openclaw#42001) with additional source PRs [#41546](openclaw/openclaw#41546), [#41552](openclaw/openclaw#41552), and [#41718](openclaw/openclaw#41718). Thanks [@wsyjh8](https://github.com/wsyjh8), [@llagy0020](https://github.com/llagy0020), [@llagy007](https://github.com/llagy007), [@pingfanfan](https://github.com/pingfanfan), and [@zheliu2](https://github.com/zheliu2). - Gateway CLI: tolerate a single transient clean WebSocket close before `hello-ok` so one-shot RPC calls reconnect instead of failing noisily, while repeated clean pre-hello closes still surface. Carries forward source PRs [#54475](openclaw/openclaw#54475) and [#54774](openclaw/openclaw#54774); [#85253](openclaw/openclaw#85253) covered adjacent connect assembly diagnostics. Thanks [@ruanrrn](https://github.com/ruanrrn). - Gateway/Linux: keep root-owned systemd user service lifecycle commands on root's user manager when a stale `SUDO_USER` remains in a root shell with root's user bus environment. Fixes [#81410](openclaw/openclaw#81410). Thanks [@Ericksza](https://github.com/Ericksza) and [@ChuckClose-tech](https://github.com/ChuckClose-tech). - Release and test reliability: extend slow Gateway/full-suite watchdogs, split local full-suite shards when throttled, stabilize plugin auth marker fixtures, avoid brittle provider-ref error text, and keep QA Lab bootstrap selection assertions aligned with flow-only scenarios. ([#92652](openclaw/openclaw#92652)) - macOS Peekaboo bridge: update the embedded Peekaboo package to 3.5.2 and route bundled-skill CLI commands through the OpenClaw app bridge so they inherit its Screen Recording and Accessibility grants. - Agent routing: route subagent RPC callbacks addressed to an agent-shaped `--to` target to the correct session key instead of falling back to the main session, so WeChat (and other channel) session-key callbacks reach the intended subagent session. ([#90231](openclaw/openclaw#90231)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Cron: preserve model, fallback, thinking, timeout, light-context, unsafe-content, and tool allow-list overrides on implicit text payloads by promoting them to agent turns, while explicit system events still prune those fields. Fixes [#28905](openclaw/openclaw#28905); carries forward [#64060](openclaw/openclaw#64060) and [#73946](openclaw/openclaw#73946). Thanks [@liaoandi](https://github.com/liaoandi). - QQBot delivery: keep markdown table chunks self-contained across message boundaries by preserving table state across block deliveries, flushing unfinished table-row fragments as plain text, and detecting short pipe-terminated rows by column count so split rows are not sent as malformed markdown. ([#92428](openclaw/openclaw#92428)) Thanks [@sliverp](https://github.com/sliverp). </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/1144

Normalize provider-qualified OpenRouter model IDs before capability lookup and transport while preserving native OpenRouter namespace IDs. Fixes openclaw#92611. Co-authored-by: liuhao1024 <[email protected]>

openclaw-barnacle Bot added extensions: openrouter size: XS proof: supplied External PR includes structured after-fix real behavior proof. labels Jun 13, 2026

liuhao1024 and others added 4 commits June 13, 2026 11:24

test(openrouter): cover normalized live tool calls

33e69d6

fix(openrouter): preserve native API model ids

e2b4000

fix(openrouter): normalize capability lookup ids

0e4be84

steipete force-pushed the fix/openrouter-anthropic-model-id branch from 7cc9d5d to 0e4be84 Compare June 13, 2026 10:55

openclaw-barnacle Bot added agents Agent runtime and tooling size: M and removed size: XS labels Jun 13, 2026

openclaw-barnacle Bot added triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. and removed proof: supplied External PR includes structured after-fix real behavior proof. labels Jun 13, 2026

steipete merged commit 6314c37 into openclaw:main Jun 13, 2026
230 of 246 checks passed

steipete mentioned this pull request Jun 13, 2026

fix(openrouter): strip openrouter/ prefix from model IDs before API calls #92644

Closed

4 tasks

github-actions Bot mentioned this pull request Jun 13, 2026

📡 Upstream Digest — 2026-06-13 13:29 UTC curtismercier/openclaw-mods#1066

Open

clawsweeper Bot mentioned this pull request Jun 20, 2026

Bug: OpenRouter model prefix duplicated when using short model IDs (openrouter/deepseek-v4-flash → openrouter/openrouter/deepseek-v4-flash) #95198

Closed

Sanjays2402 mentioned this pull request Jun 20, 2026

fix(openrouter): expand short DeepSeek V4 aliases to upstream slug in API normalizer (#95198) #95202

Closed

maweibin mentioned this pull request Jun 20, 2026

fix(openrouter): strip provider prefix from short model refs in API model ID normalization #95208

Closed

23 tasks

clawsweeper Bot mentioned this pull request Jul 6, 2026

Models: fully dynamic model discovery (OpenRouter + beyond) #10687

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(openrouter): strip openrouter/ prefix from model ID in normalizeResolvedModel hook (fixes #92611)#92627

fix(openrouter): strip openrouter/ prefix from model ID in normalizeResolvedModel hook (fixes #92611)#92627
steipete merged 4 commits into
openclaw:mainfrom
liuhao1024:fix/openrouter-anthropic-model-id

liuhao1024 commented Jun 13, 2026 •

edited by steipete

Loading

Uh oh!

clawsweeper Bot commented Jun 13, 2026 •

edited

Loading

Uh oh!

steipete commented Jun 13, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Uh oh!

Conversation

liuhao1024 commented Jun 13, 2026 • edited by steipete Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Verification

Real behavior proof

Release-note context

Uh oh!

clawsweeper Bot commented Jun 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

steipete commented Jun 13, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

liuhao1024 commented Jun 13, 2026 •

edited by steipete

Loading

clawsweeper Bot commented Jun 13, 2026 •

edited

Loading